© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 10166
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals working in an advisory role

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals serving in advisory positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tons
    -0.74
    Loc
    -0.69
    cats
    -0.63
    days
    -0.63
     loud
    -0.61
    paces
    -0.60
     Broken
    -0.59
     Shall
    -0.59
    holes
    -0.58
    humans
    -0.58
    POSITIVE LOGITS
     adviser
    3.49
     advisor
    3.14
     Adviser
    2.72
     advisers
    2.50
     Advisor
    2.32
     advisors
    2.25
     aide
    1.92
     counselor
    1.90
     strategist
    1.73
     consultant
    1.68
    Activations Density 0.016%

    No Known Activations